Related papers: GRAPE-6: A Petaflops Prototype

In this case study, we investigate the impact of workload balance on the performance of multi-FPGA codes. We start with an application in which two distinct kernels run in parallel on two SRC-6 MAP processors. We observe that one of the MAP…

Fault tolerance overhead of high performance computing (HPC) applications is becoming critical to the efficient utilization of HPC systems at large scale. HPC applications typically tolerate fail-stop failures by checkpointing. Another…

Scaling up hardware systems has become an important tactic for improving performance as Moore's law fades. Unfortunately, simulations of large hardware systems are often a design bottleneck due to slow throughput and long build times. In…

Computing has a huge memory problem. The memory system, consisting of multiple technologies at different levels, is responsible for most of the energy consumption, performance bottlenecks, robustness problems, monetary cost, and hardware…

We discuss the hardware design choices made in our 16K-node 0.8 Teraflops supercomputer project, a machine architecture optimized for full QCD calculations. The efficiency of the conjugate gradient algorithm in terms of balance of…

While the HPC community is working towards the development of the first Exaflop computer (expected around 2020), after reaching the Petaflop milestone in 2008 still only few HPC applications are able to fully exploit the capabilities of…

Large-scale graph problems are of critical and growing importance and historically parallel architectures have provided little support. In the spirit of co-design, we explore the question, How fast can graph computing go on a fine-grained…

Mobile systems are embracing heterogeneous architectures by getting more types of cores and more specialized cores, which allows applications to be faster and more efficient. We aim at exploiting the hardware heterogeneity from the browser…

Last level cache management and core interconnection network play important roles in performance and power consumption in multicore system. Large scale chip multicore uses mesh interconnect widely due to scalability and simplicity of the…

The continuous growth of big data applications with high computational and scalability demands has resulted in increasing popularity of cloud computing. Optimizing the performance and power consumption of cloud resources is therefore…

Current approaches to scheduling workloads on heterogeneous systems with specialized accelerators often rely on manual partitioning, offloading tasks with specific compute patterns to accelerators. This method requires extensive…

This experience report analyses a one year project focused on building a distributed real-time analytics system using edge computing and machine learning. The project faced critical setbacks due to a big-bang integration approach, where all…

We present a new approach to fault tolerance for High Performance Computing system. Our approach is based on a careful adaptation of the Algorithmic Based Fault Tolerance technique (Huang and Abraham, 1984) to the need of parallel…

The deployment of the next generation computing platform at ExaFlops scale requires to solve new technological challenges mainly related to the impressive number (up to 10^6) of compute elements required. This impacts on system power…

Heterogeneous many-cores are now an integral part of modern computing systems ranging from embedding systems to supercomputers. While heterogeneous many-core design offers the potential for energy-efficient high-performance, such potential…

Training transformer models requires substantial GPU compute and memory resources. In homogeneous clusters, distributed strategies allocate resources evenly, but this approach is inefficient for heterogeneous clusters, where GPUs differ in…

Parallel processing, the core of High Performance Computing (HPC), was and still the most effective way in improving the speed of computer systems. For the past few years, the substantial developments in the computing power of processors…

Many important computational problems require utilization of high performance computing (HPC) systems that consist of multi-level structures combining higher and higher numbers of devices with various characteristics. Utilizing full power…

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

Shrinking transistors, which powered the advancement of computing in the past half century, has stalled due to power wall; now extreme heterogeneity is promised to be the next driving force to feed the needs of ever-increasingly diverse…